AI Agents and Hard Choices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Wang, Kangyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918455681220608
author Wang, Kangyu
author_facet Wang, Kangyu
contents Can AI agents deal with hard choices -- cases where options are incommensurable because multiple objectives are pursued simultaneously? Adopting a technologically engaged approach distinct from existing philosophical literature, I submit that the fundamental design of current AI agents as optimisers creates two limitations: the Identification Problem and the Resolution Problem. First, I demonstrate that agents relying on Multi-Objective Optimisation (MOO) are structurally unable to identify incommensurability. This inability generates three specific alignment problems: the blockage problem, the untrustworthiness problem, and the unreliability problem. I argue that standard mitigations, such as Human-in-the-Loop, are insufficient for many decision environments. As a constructive alternative, I conceptually explore an ensemble solution. Second, I argue that even if the Identification Problem is solved, AI agents face the Resolution Problem: they lack the autonomy to resolve hard choices rather than arbitrarily picking through self-modification of objectives. I conclude by examining the opaque normative trade-offs involved in granting AI this level of autonomy.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15304
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI Agents and Hard Choices
Wang, Kangyu
Artificial Intelligence
Computers and Society
I.2.0; K.4.1
Can AI agents deal with hard choices -- cases where options are incommensurable because multiple objectives are pursued simultaneously? Adopting a technologically engaged approach distinct from existing philosophical literature, I submit that the fundamental design of current AI agents as optimisers creates two limitations: the Identification Problem and the Resolution Problem. First, I demonstrate that agents relying on Multi-Objective Optimisation (MOO) are structurally unable to identify incommensurability. This inability generates three specific alignment problems: the blockage problem, the untrustworthiness problem, and the unreliability problem. I argue that standard mitigations, such as Human-in-the-Loop, are insufficient for many decision environments. As a constructive alternative, I conceptually explore an ensemble solution. Second, I argue that even if the Identification Problem is solved, AI agents face the Resolution Problem: they lack the autonomy to resolve hard choices rather than arbitrarily picking through self-modification of objectives. I conclude by examining the opaque normative trade-offs involved in granting AI this level of autonomy.
title AI Agents and Hard Choices
topic Artificial Intelligence
Computers and Society
I.2.0; K.4.1
url https://arxiv.org/abs/2504.15304